Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2966 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.8261. Min Act: -0.0000

Data Index: 247978 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.8280. Min Act: -0.0000

Data Index: 1295842 (C4 (Web Text))

Max Activating Token Index: 949

Text #2

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.7578. Min Act: -0.0000

Data Index: 614042 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.7083. Min Act: -0.0001

Data Index: 248651 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.5722. Min Act: -0.0000

Data Index: 1110965 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.7003. Min Act: -0.0000

Data Index: 875931 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.5320. Min Act: -0.0001

Data Index: 1091363 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.6657. Min Act: -0.0000

Data Index: 71473 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.4891. Min Act: -0.0000

Data Index: 1199799 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.6461. Min Act: -0.0000

Data Index: 614757 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.6292. Min Act: -0.0000

Data Index: 728891 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.7645. Min Act: -0.0000

Data Index: 1036978 (C4 (Web Text))

Max Activating Token Index: 979

Text #12

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.6080. Min Act: -0.0000

Data Index: 427949 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.5879. Min Act: -0.0000

Data Index: 1019126 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.4663. Min Act: -0.0000

Data Index: 905491 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.4670. Min Act: -0.0000

Data Index: 766479 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.5663. Min Act: -0.0001

Data Index: 103703 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.4395. Min Act: -0.0000

Data Index: 829737 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.5266. Min Act: -0.0000

Data Index: 229843 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.5252. Min Act: -0.0000

Data Index: 630065 (C4 (Web Text))

Max Activating Token Index: 946